Samia Kouki

Dr. Samia Kouki


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022
Verified
Book Chapter
Closed access
PDF file
SKSamia Kouki
Samia Kouki
MSMouza Al Shemaili
Mouza Al Shemaili

26 September 2026 in Future Internet
Verified
Journal Article
Open access
PDF file
ASAshutosh Shankhdhar
Ashutosh Shankhdhar
VMVanitha Murugesan
Vanitha Murugesan
TEThenmozhi E
Thenmozhi E
SKSamia Kouki
Samia Kouki
SYSumendra Yogarayan
Sumendra Yogarayan
PKPrabu Kaliyaperumal
Prabu Kaliyaperumal
The increasing heterogeneity of Internet of Things (IoT) environments makes intrusion diagnosis challenging because device behaviours, traffic patterns, and attack distributions can vary across deployment conditions, while data-locality requirements limit centralized access to network data. This study proposes CA-AFiD (Context-Aware Adaptive Federated Intrusion Diagnosis), a framework designed to support adaptive and interpretable intrusion diagnosis across IoT–Fog–Cloud environments. CA-AFiD combines behaviour-aware representation learning using Transformer, BiLSTM, and attention mechanisms with a context-aware adaptive ensemble that adjusts learner contributions according to behavioural complexity, attack density, and device context. Federated learning is used to coordinate model updates across distributed Fog nodes without sharing raw traffic data, while attention-based interpretation, SHAP feature attribution, and ATT&CK-oriented contextualization provide explanatory information for diagnostic decisions. The framework was evaluated on the CIC-IoT-DIAD 2024 dataset across device-aware learning, imbalanced attack diagnosis, temporal sensitivity, federated learning, explainability, and operational-efficiency scenarios. Under the controlled homogeneous evaluation, the complete CA-AFiD framework achieved a 99.22% F1-score, while the heterogeneous evaluation achieved an overall 99.03% F1-score across the evaluated attack categories. Across the four evaluated minority attack categories, the average F1-score was 98.79%. Under federated learning, the global model achieved an average device-identification accuracy of 98.90% and an average anomaly-diagnosis F1-score of 98.90% across the participating Fog nodes, while ATT&CK mapping achieved 88–98% coverage. These results demonstrate the potential of CA-AFiD to provide adaptive, data-local, and interpretable intrusion diagnosis for heterogeneous IoT–Fog–Cloud environments.

1 January 2026 in Nursing Forum
Verified
Journal Article
Open access
PDF file
HKHeba Khalil
Heba Khalil
RAReem Almehrzi
Reem Almehrzi
ARAyda Rezaei
Ayda Rezaei
EAEsra Adil
Esra Adil
AAAmal Alashraf
Amal Alashraf
KYKhalil M. Yousef
Khalil M. Yousef
Background: ChatGPT and other generative AI tools are increasingly used in healthcare education, yet evidence on nursing students’ adoption during their clinical training remains limited. This study examined undergraduate nursing students’ patterns of ChatGPT use, perceived usefulness, ease of use, risks, and the role of faculty and institutional support in clinical learning. Methods: A cross‐sectional survey was conducted with 218 nursing students at a UAE university. The questionnaire assessed ChatGPT use across clinical tasks, perceptions, ethical concerns, faculty encouragement, institutional guidance, and barriers. Hierarchical regression analysis identified predictors of ChatGPT usage behavior. Results: ChatGPT use was widespread: 76% of students used it mainly for understanding clinical cases (81%), clinical assignments and documentation (77%), and exam preparation (73%). Ethical concerns were reported by 61% of students, including misinformation (60%) and over‐reliance (55%). Faculty encouragement was reported by 60%, while 52% noted institutional guidelines. Regression analysis showed that perceived usefulness ( β = 0.55, p < 0.001), ease of use ( β = 0.30, p < 0.001), and faculty encouragement ( β = 0.11, p = 0.029) significantly predicted usage, explaining 66.4% of the variance. Institutional guidelines and demographics were not significant predictors. Most students (83%) expressed interest in ChatGPT training, and 86% supported AI integration into the curriculum. Conclusion: Nursing students actively use and value ChatGPT in clinical learning. Adoption is strongly influenced by perceived usefulness, ease of use, and faculty support. Ethical concerns and limited institutional guidance highlight the need for structured support, faculty development, and clear policies to ensure responsible and effective AI integration in clinical nursing education.

8 October 2026 in Discover Computing
Verified
Journal Article
Open access
PDF file
PSPriya S
Priya S
KTK. Tamilarasi
K. Tamilarasi
VSVivek Kumar Sharma
Vivek Kumar Sharma
PKPrabu Kaliyaperumal
Prabu Kaliyaperumal
BBBalamurugan Balusamy
Balamurugan Balusamy
AEArun Kumar Elengovan
Arun Kumar Elengovan
Cloud computing is a fundamental paradigm in modern computing; however, its distributed and multi-tenant nature increases exposure to cyber threats, making effective intrusion detection essential. Despite recent advances in artificial intelligence–based intrusion detection systems (IDS), many existing approaches remain sensitive to class imbalance, computationally demanding, and insufficiently robust under large-scale network traffic conditions. To address these challenges, this paper proposes an AI-driven intrusion detection framework, termed Secured Deep Generative Adversarial Rat-Optimized Diagonal Matrix (SDGA-RODM), designed for efficient intrusion detection in large-scale cloud network traffic environments. The proposed framework integrates three key components: (i) a mean divergence regularization (MDR)–based preprocessing strategy to mitigate class imbalance without altering intrinsic data distributions; (ii) a rat-optimized diagonal matrix score (RODMS)–based feature selection mechanism to derive compact and discriminative feature subsets; and (iii) a Wasserstein generative adversarial learning–based classifier (DWGALC) to enhance robustness under complex and imbalanced attack patterns. Extensive experiments conducted on the LUFlow and CIC-IDS-2017 benchmark datasets demonstrate that SDGA-RODM achieves improved performance compared with the evaluated representative IDS methods, including deep learning, ensemble-based, and optimization-driven approaches, achieving up to 6–8% improvement in detection accuracy, 15–40% reduction in classification error, and up to 30% reduction in training time under imbalanced traffic conditions. These results indicate that SDGA-RODM provides an effective and computationally efficient intrusion detection framework, demonstrating promising performance and robustness under controlled benchmark and simulation-based settings representative of cloud network traffic environments.


22 October 2026 in Future Internet
Verified
Journal Article
Open access
PDF file
SKSamia Kouki
Samia Kouki
FKFiroz Khan
Firoz Khan
NSNithya Rekha Sivakumar
Nithya Rekha Sivakumar
RAR. Anbarasu
R. Anbarasu
PKPrabu Kaliyaperumal
Prabu Kaliyaperumal
RPRajakumar Perumal
Rajakumar Perumal
This study investigates whether learning behaviour in DDoS intrusion detection is determined solely by learning architecture or is also influenced by how the investigated network traffic is represented. A representation-aware experimental methodology is developed in which traffic representation is treated as the primary manipulated factor within each benchmark dataset, while benchmark harmonization, preprocessing, learning architectures, and evaluation protocols are controlled. Three complementary representations—Flow, Header, and Hybrid—are constructed from the same selected traffic instances within each benchmark dataset and evaluated using five representative machine learning and deep learning architectures. Predictive performance, experimental reproducibility, cross-representation stability, confidence calibration, and representation sensitivity are assessed using repeated experiments and statistical validation. The results show systematic differences across representations in predictive performance, cross-representation stability, calibration, and representation sensitivity under the controlled experimental conditions. These findings indicate that traffic representation is associated with differences in the discriminative structures made computationally available to learning algorithms rather than serving solely as a preprocessing mechanism. Based on these observations, the Representation-Dependent Discriminative Structure Principle (RDDSP) is proposed as a context-specific conceptual hypothesis describing how representation-exposed discriminative structures may interact with the inductive characteristics of learning architectures to shape learning behaviour in the investigated DDoS intrusion-detection setting. The empirical evaluation is restricted to a common attack space comprising SYN Flood and UDP Flood, together with Benign traffic, and uses a controlled, class-balanced evaluation distribution. Broader applicability of the findings and RDDSP remains subject to validation across additional attack categories, independently collected datasets, and operationally representative class-prevalence distributions.